wq1315 Goto Github PK

2019-ccf-bdci-ocr-mczj-ocr-identificationidelement

2019CCF-BDCI大赛 最佳创新探索奖获得者 基于OCR身份证要素提取赛题冠军 天晨破晓团队 赛题源码

annotated-transformer

http://nlp.seas.harvard.edu/2018/04/03/attention.html

attentionlayers

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

bert4keras

keras implement of transformers for humans

chinese-ocr

[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

classyvision

An end-to-end PyTorch framework for image and video classification

conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning

crawler_illegal_cases_in_china

Collection of China illegal cases about web crawler 本项目用来整理所有**大陆爬虫开发者涉诉与违规相关的新闻、资料与法律法规。致力于帮助在**大陆工作的爬虫行业从业者了解我国相关法律，避免触碰数据合规红线。 [AD]中文知识图谱门户

cvpr2023-papers-with-code

CVPR 2023 论文和开源项目合集

da-crf

This is a implementation of "动态注意力机制：一种面向属性抽取的CRF优化器分类方法"

deep-learning-interview-book

深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

fooocus

Focus on prompting and generating

gnnpapers

Must-read papers on graph neural networks (GNN)

google-landmark

Dataset with 5 million images depicting human-made and natural landmarks spanning 200 thousand classes.

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

identificationcodes

idm-vton

IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

ipyvolume

3d plotting for Python in the Jupyter notebook based on IPython widgets using WebGL

knowledgegraph

mokecompetition

my_orc_keras_verification_code_identification

本项目实现了ocr主流算法gru/lstm+ctc+cnn架构，进行不定长度验证码识别，达到不分割字符而识别验证码内容的效果。验证码内容包含了大小字母以及数字，并增加点、线、颜色、位置、字体等干扰项。本项目对gru +ctc+cnn、lstm+ctc+cnn、cnn三种架构进行了对比，实践说明同等训练下gru/lstm+ctc+cnn架构准确率和速度均明显优于cnn架构，gru +ctc+cnn优于lstm+ctc+cnn，在实验2500个样本数据200轮训练时，gru +ctc+cnn架构在500样本测试准确率达90.2%。本项目技术能够训练长序列的ocr识别，更换数据集和相关调整，即可用于比如身份证号码、车牌、手机号、邮编等识别任务，也可用于汉字识别。

open-sora-plan

This project aim to reproducing Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.

pumpkin-book

《机器学习》（西瓜书）公式推导解析，在线阅读地址：https://datawhalechina.github.io/pumpkin-book

r-drop

rainbow-is-all-you-need

Rainbow is all you need! Step-by-step tutorials from DQN to Rainbow

segment-everything-everywhere-all-at-once

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

selenium

sentimentanalysis

solr